candidate-reproduction SKILL.md skillA
candidate-reproduction from fourteen1416/academic-agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fourteen1416/academic-agent-toolkit/candidate-reproduction@git:20261024.075a053Pins git:20261024.075a053 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fourteen1416/academic-agent-toolkit
- Path
academic-toolkit/skills/candidate-reproduction/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261024.075a053, committed Oct 24, 2026
- Size
- 4,710 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
候选交付复现：按引擎生成的复现计划在独立目录重跑候选冻结 recipe，逐目标核对结果并产出复现报告。触发词：候选复现、复现计划、candidate reproduction、冻结 recipe 重跑。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 候选交付·复现（冻结 recipe 的真实重跑） **为什么需要这一步**：promotion 只冻结候选的输入、产物、谱系与命令 recipe，不重跑生产步骤。交付工作流必须证明「同一份冻结 recipe 在干净目录里仍能产出同一字节」，否则候选只是历史文件快照。本步由引擎分派，输出 `REPRODUCTION_REPORT.json`；没有真实重跑（no-op、复用旧字节、手写报告）一律不算复现。 ## 输入（引擎已生成，不要手改） - `REPRODUCTION_PLAN.json`：工作区根目录，引擎在 `start --candidate` 时写入。 - `candidate_id`：本次交付候选。 - `targets[]`：每项含 `target`（工作区相对路径）、`recipe_id`、`spec`（候选冻结 recipe 的原样副本）。 - 同一 `recipe_id` 可能覆盖多个 target；**一条命令只跑一次**。 - 会话 `context` 返回的 `delivery_candidate_id` 与 plan 内 `candidate_id` 必须一致；不一致时停止并报告，不要自行猜测。 ## 执行（唯一合法入口） ```bash python -m engine.workflow_cli session reproduce \ --session .engine/sessions/<attempt_id>.json \ --plan REPRODUCTION_PLAN.json \ --candidate <candidate_id> ``` 引擎内部完成（不要手工重做其中任何一步）： 1. 从候选冻结数据读取 recipe 与 target 冻结 sha；plan 的 recipe 与候选冻结值不一致时直接拒绝。 2. 每个 recipe 新建 `_reproduction/<candidate_id>/<recipe_hash>/<attempt_id>/<submission_id>/`；`submission_id` 每次调用新生成，**重试也不会复用旧目录**。 3. 复制该 recipe 的冻结输入（含 `inputs_snapshot` 中的脚本/配置）到复现目录并逐项校验 sha。 4. 非 `mutates` 输出断言运行前不存在；`mutates` 输出允许存在，但 before 必须等于候选冻结的输入版本。 5. 绝对路径 argv token 映射到复现目录；相对 token 原样保留；工作区外绝对路径拒绝。 …
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/candidate-reproduction@sha256:4c2b7dd90db6b9a0The line at the top of this page pins the label git:20261024.075a053, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_k7cqwfajszltb7mx)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 24, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4710 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
fourteen1416/academic-agent-toolkit · 12 stars · license a license file GitHub does not identify · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_k7cqwfajszltb7mx GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/candidate-reproduction GET https://markdownregistry.com/api/v1/blob/4c2b7dd90db6b9a00bba110785061da5160a1a10d92ff5e0b1264ae3d58dd5d6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.